rohitg00/ai-engineering-from-scratch resource

Health v2 · maintenance only

Flags: young

Adoption not part of the score

49577 stars · 8628 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A free, MIT-licensed open-source curriculum of 511 lessons across 20 phases (~329 hours) that teaches AI engineering by building every core algorithm from raw math before using frameworks. Lessons span linear algebra to autonomous agents in Python, TypeScript, Rust, and Julia, each producing a reusable artifact like a prompt, skill, agent, or MCP server.

Use cases

• learn AI engineering from scratch
• understand how transformers and attention work internally
• build agents and MCP servers by hand
• study backpropagation and tokenizers from raw math
• find a structured alternative to scattered AI tutorials
• prepare for a professional AI engineering role
• learn deep learning without frameworks first

When to choose

• you want deep foundational understanding of AI algorithms, not just framework usage
• you prefer self-paced, free, open-source learning material
• you want lessons that produce reusable artifacts like prompts, skills, and MCP servers
• you want curriculum usable with AI coding agents via SKILL.md

When to avoid

• you need a quick framework-specific tutorial like 'fine-tune with PyTorch in an hour'
• you want instructor-led or accredited courses with certificates
• you need production-ready software rather than educational material

Facets

learning-resource · maturity active

machine-learning deep-learning nlp agent-framework mcp prompt-engineering computer-vision llm-training artificial-intelligence machine-learning deep-learning large-language-models education tutorials python rust cross-platform cli curriculum from-scratch generative-ai transformers agents mcp-servers self-paced-learning open-courseware ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rohitg00/ai-engineering-from-scratch")